Over the past few years, research teams worldwide have been working on technologies to interpret animal communication. A research group in Denmark has taken a different approach, developing a technology that can recognize animal emotions.

Scientists from the Department of Biology at the University of Copenhagen have successfully trained a machine-learning model to distinguish between positive and negative emotions in seven different animal species. These include two horse species, sheep, pigs, wild boars, goats, and cows. This research paves the way for artificial intelligence to help us understand the emotions of animals.

According to the study published in the journal iScience, the AI model analyzed vocalization patterns and achieved an impressive accuracy of 89.49%. This marks the first research effort to detect emotional intensity across species using artificial intelligence.

By examining thousands of animal vocalizations in different emotional states, the researchers identified key acoustic indicators of emotional intensity. The most significant factors in determining whether an emotion was positive or negative included variations in duration, energy distribution, fundamental frequency, and amplitude modulation. Notably, these patterns remained consistent across all species, suggesting that fundamental vocal expressions of emotions have been evolutionarily preserved.

“This groundbreaking discovery provides strong evidence that AI can decode emotions across multiple species based on vocal patterns. It has the potential to revolutionize animal welfare, conservation efforts, and livestock management by enabling real-time monitoring of animal emotions,” said Elodie Briefer, Associate Professor at the Department of Biology and a member of the research team.